llama : pin mmap-backed CPU weights for faster H2D uploads

Wire the existing GGML_CUDA_REGISTER_HOST path back up: after model load,
cudaHostRegister the mmap pages backing weights kept in system memory.
Recovers pageable-copy losses when MoE experts are streamed to the GPU
during prefill (n-cpu-moe): Qwen3.6-35B-A3B pp2048 1144 -> 1385 t/s on
RTX 3060. Opt-in via GGML_CUDA_REGISTER_HOST=1, unchanged otherwise.

src/llama-mmap.cpp

@@ -618,13 +618,47 @@ struct llama_mmap::impl {
 };
 
 llama_mmap::llama_mmap(struct llama_file * file, size_t prefetch, bool numa) : pimpl(std::make_unique<impl>(file, prefetch, numa)) {}
-llama_mmap::~llama_mmap() = default;
+
+llama_mmap::~llama_mmap() {
+    // unpin before the pages are unmapped by the impl destructor
+    if (host_reg_addr && host_unreg_fn) {
+        host_unreg_fn(host_reg_addr);
+    }
+}
 
 size_t llama_mmap::size() const { return pimpl->size; }
 void * llama_mmap::addr() const { return pimpl->addr; }
 
 void llama_mmap::unmap_fragment(size_t first, size_t last) { pimpl->unmap_fragment(first, last); }
 
+size_t llama_mmap::register_host(size_t first, size_t last, bool (*reg_fn)(void *, size_t), void (*unreg_fn)(void *)) {
+#ifdef _POSIX_MAPPED_FILES
+    if (host_reg_addr || !reg_fn || !unreg_fn || last <= first) {
+        return 0;
+    }
+
+    // expand outward to the page boundaries retained by unmap_fragment
+    const size_t page_size = sysconf(_SC_PAGESIZE);
+    first = first & ~(page_size - 1);
+    last  = (last + page_size - 1) & ~(page_size - 1);
+
+    void * reg_addr = (uint8_t *) pimpl->addr + first;
+    if (!reg_fn(reg_addr, last - first)) {
+        return 0;
+    }
+
+    host_reg_addr  = reg_addr;
+    host_unreg_fn  = unreg_fn;
+    return last - first;
+#else
+    GGML_UNUSED(first);
+    GGML_UNUSED(last);
+    GGML_UNUSED(reg_fn);
+    GGML_UNUSED(unreg_fn);
+    return 0;
+#endif
+}
+
 #if defined(_POSIX_MEMLOCK_RANGE) || defined(_WIN32)
 const bool llama_mmap::SUPPORTED  = true;
 #else

src/llama-mmap.h

@@ -50,11 +50,19 @@ struct llama_mmap {
 
     void unmap_fragment(size_t first, size_t last);
 
+    // pin the pages backing [first, last) with a backend allocator for faster H2D copies,
+    // unpinned in the destructor before the pages are unmapped
+    // returns the number of bytes registered, 0 on failure
+    size_t register_host(size_t first, size_t last, bool (*reg_fn)(void *, size_t), void (*unreg_fn)(void *));
+
     static const bool SUPPORTED;
 
 private:
     struct impl;
     std::unique_ptr<impl> pimpl;
+
+    void * host_reg_addr = nullptr;
+    void (*host_unreg_fn)(void *) = nullptr;
 };
 
 struct llama_mlock {

src/llama-model-loader.cpp

@@ -1677,6 +1677,15 @@ bool llama_model_loader::load_all_data(
     if (size_done >= size_data) {
         // unmap offloaded tensors and metadata
         if (use_mmap) {
+            // pin the pages backing the weights kept in system memory for faster H2D copies
+            bool (*reg_fn)(void *, size_t) = nullptr;
+            void (*unreg_fn)(void *) = nullptr;
+            for (size_t i = 0; i < ggml_backend_dev_count() && !reg_fn; i++) {
+                ggml_backend_reg_t reg = ggml_backend_dev_backend_reg(ggml_backend_dev_get(i));
+                reg_fn   = (bool (*)(void *, size_t)) ggml_backend_reg_get_proc_address(reg, "ggml_backend_register_host_buffer");
+                unreg_fn = (void (*)(void *))         ggml_backend_reg_get_proc_address(reg, "ggml_backend_unregister_host_buffer");
+            }
+
             for (uint32_t idx = 0; idx < mappings.size(); idx++) {
                 const auto & mmap_used = mmaps_used.at(idx);
                 auto & mapping = mappings.at(idx);
@@ -1684,6 +1693,13 @@ bool llama_model_loader::load_all_data(
                 if (mmap_used.second != 0) {
                     mapping->unmap_fragment(mmap_used.second, mapping->size());
                 }
+                if (mmap_used.second > mmap_used.first) {
+                    size_t n_registered = mapping->register_host(mmap_used.first, mmap_used.second, reg_fn, unreg_fn);
+                    if (n_registered > 0) {
+                        LLAMA_LOG_INFO("%s: pinned %.2f MiB of mapped model memory for faster H2D transfers\n",
+                                __func__, n_registered / 1024.0 / 1024.0);
+                    }
+                }
             }
         }
         if (progress_callback) {